
pip install sodapy

Collecting sodapy
  Downloading sodapy-2.2.0-py2.py3-none-any.whl (15 kB)
Collecting requests>=2.28.1
  Downloading requests-2.31.0-py3-none-any.whl (62 kB)
     |████████████████████████████████| 62 kB 1.8 MB/s eta 0:00:01
Requirement already satisfied: urllib3<3,>=1.21.1 in /Users/aidan/opt/anaconda3/lib/python3.9/site-packages (from requests>=2.28.1->sodapy) (1.26.7)
Requirement already satisfied: idna<4,>=2.5 in /Users/aidan/opt/anaconda3/lib/python3.9/site-packages (from requests>=2.28.1->sodapy) (3.2)
Requirement already satisfied: certifi>=2017.4.17 in /Users/aidan/opt/anaconda3/lib/python3.9/site-packages (from requests>=2.28.1->sodapy) (2021.10.8)
Requirement already satisfied: charset-normalizer<4,>=2 in /Users/aidan/opt/anaconda3/lib/python3.9/site-packages (from requests>=2.28.1->sodapy) (2.0.4)
Installing collected packages: requests, sodapy
  Attempting uninstall: requests
    Found existing installation: requests 2.26.0
    Uninstalling requests-2.26.0:
      Successfully uninstalled requests-2.26.0
ERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.
conda-repo-cli 1.0.4 requires pathlib, which is not installed.
anaconda-project 0.10.1 requires ruamel-yaml, which is not installed.
Successfully installed requests-2.31.0 sodapy-2.2.0
Note: you may need to restart the kernel to use updated packages.


import pandas as pd
from sodapy import Socrata

/Users/aidan/opt/anaconda3/lib/python3.9/site-packages/pandas/core/computation/expressions.py:21: UserWarning: Pandas requires version '2.8.0' or newer of 'numexpr' (version '2.7.3' currently installed).
  from pandas.core.computation.check import NUMEXPR_INSTALLED
/Users/aidan/opt/anaconda3/lib/python3.9/site-packages/pandas/core/arrays/masked.py:62: UserWarning: Pandas requires version '1.3.4' or newer of 'bottleneck' (version '1.3.2' currently installed).
  from pandas.core import (


client = Socrata("data.cityofchicago.org", None)

results = client.get("85ca-t3if", where="CRASH_DATE > '2022-01-01'")

# Convert to pandas DataFrame
crash_raw = pd.DataFrame.from_records(results)

WARNING:root:Requests made without an app_token will be subject to strict throttling limits.


crash_raw.columns

Index(['crash_record_id', 'crash_date', 'posted_speed_limit',
       'traffic_control_device', 'device_condition', 'weather_condition',
       'lighting_condition', 'first_crash_type', 'trafficway_type',
       'alignment', 'roadway_surface_cond', 'road_defect', 'report_type',
       'crash_type', 'hit_and_run_i', 'damage', 'date_police_notified',
       'prim_contributory_cause', 'sec_contributory_cause', 'street_no',
       'street_direction', 'street_name', 'beat_of_occurrence', 'num_units',
       'most_severe_injury', 'injuries_total', 'injuries_fatal',
       'injuries_incapacitating', 'injuries_non_incapacitating',
       'injuries_reported_not_evident', 'injuries_no_indication',
       'injuries_unknown', 'crash_hour', 'crash_day_of_week', 'crash_month',
       'latitude', 'longitude', 'location', 'intersection_related_i',
       'statements_taken_i', 'photos_taken_i', 'private_property_i',
       'crash_date_est_i', 'dooring_i', 'work_zone_i', 'work_zone_type',
       'workers_present_i'],
      dtype='object')


# convert the 'Date' column to datetime format
crash_raw['crash_date'] = pd.to_datetime(crash_raw['crash_date'])
crash_raw['injuries'] = (pd.to_numeric(crash_raw['injuries_total']) > 0)

crash = crash_raw[['crash_date', 'injuries', 'latitude', 'longitude']]


crash_raw.columns

Index(['crash_record_id', 'crash_date', 'posted_speed_limit',
       'traffic_control_device', 'device_condition', 'weather_condition',
       'lighting_condition', 'first_crash_type', 'trafficway_type',
       'alignment', 'roadway_surface_cond', 'road_defect', 'report_type',
       'crash_type', 'hit_and_run_i', 'damage', 'date_police_notified',
       'prim_contributory_cause', 'sec_contributory_cause', 'street_no',
       'street_direction', 'street_name', 'beat_of_occurrence', 'num_units',
       'most_severe_injury', 'injuries_total', 'injuries_fatal',
       'injuries_incapacitating', 'injuries_non_incapacitating',
       'injuries_reported_not_evident', 'injuries_no_indication',
       'injuries_unknown', 'crash_hour', 'crash_day_of_week', 'crash_month',
       'latitude', 'longitude', 'location', 'intersection_related_i',
       'statements_taken_i', 'photos_taken_i', 'private_property_i',
       'crash_date_est_i', 'dooring_i', 'work_zone_i', 'work_zone_type',
       'workers_present_i', 'injuries'],
      dtype='object')


# Assuming 'crash_raw' is your original DataFrame
selected_columns = ['longitude', 'latitude', 'injuries', 'lighting_condition', 'weather_condition', 'crash_month', 'prim_contributory_cause', 'sec_contributory_cause','crash_date']

# Create a new DataFrame with only the selected columns
crash_filtered = crash_raw[selected_columns]


# Drop rows where 'latitude' or 'longitude' is NaN
crash_filtered = crash_filtered.dropna(subset=['latitude', 'longitude'])


crash_raw['injuries']

0      False
1      False
2      False
3      False
4      False
       ...  
995    False
996    False
997    False
998    False
999    False
Name: injuries, Length: 1000, dtype: bool


crash_raw['longitude']

0      -87.775099001
1      -87.631851672
2      -87.633011933
3      -87.675292438
4      -87.753893377
           ...      
995    -87.624252186
996    -87.767138108
997    -87.687248767
998     -87.76844737
999    -87.651162183
Name: longitude, Length: 1000, dtype: object


import matplotlib.pyplot as plt

# Assuming 'latitude', 'longitude', and 'injuries' are columns in your DataFrame
latitudes = crash_filtered['latitude'].astype(float)
longitudes = crash_filtered['longitude'].astype(float)
injuries = crash_filtered['injuries']

# Convert injuries to numeric values (boolean to int)
injuries_numeric = injuries.astype(int)

# Create separate scatter plots for 'Injuries' and 'No Injuries'
plt.scatter(longitudes[injuries_numeric == 1], latitudes[injuries_numeric == 1], c='red', marker='o', label='Injuries', alpha=0.6)
plt.scatter(longitudes[injuries_numeric == 0], latitudes[injuries_numeric == 0], c='green', marker='o', label='No Injuries', alpha=0.6)

# Set labels and title
plt.xlabel('Longitude')
plt.ylabel('Latitude')
plt.title('Chicago Car Crashes')

# Add legend
plt.legend()

# Show the plot
plt.show()
plt.savefig('crash_data_visualization.jpg')

<Figure size 432x288 with 0 Axes>


import matplotlib.pyplot as plt
import pandas as pd

# Assuming 'prim_contributory_cause' and 'sec_contributory_cause' are columns in your DataFrame
combined_causes = pd.concat([crash_filtered['prim_contributory_cause'], crash_filtered['sec_contributory_cause']])

# Filter out 'UNABLE TO DETERMINE' and 'NOT APPLICABLE'
filtered_causes = combined_causes[~combined_causes.isin(['UNABLE TO DETERMINE', 'NOT APPLICABLE'])]

# Count the occurrences of each cause
cause_counts = filtered_causes.value_counts()

# Create a bar chart
plt.bar(cause_counts.head(5).index, cause_counts.head(5), color='blue')
plt.xlabel('Contributory Causes')
plt.ylabel('Frequency')
plt.title('Top 5 Contributory Causes to Car Crashes')
plt.xticks(rotation=30)  # Rotate x-axis labels for better visibility

# Show the plot
plt.show()
plt.savefig('Causes_Ranked.jpg')

<Figure size 432x288 with 0 Axes>


crash_filtered


import pandas as pd

# Assuming 'crash_filtered' is your DataFrame with a 'crash_date' column
crash_filtered['year'] = crash_filtered['crash_date'].dt.year

# Now 'crash_filtered' has a new column 'year' containing the year of each crash
crash_filtered


import matplotlib.pyplot as plt
import pandas as pd

# Assuming 'crash_filtered' is your DataFrame with the 'year' and 'crash_month' columns
# Group by year and month and count crashes
crashes_by_year_month = crash_filtered.groupby(['year', 'crash_month']).size().unstack()

# Create a grouped bar chart
crashes_by_year_month.plot(kind='bar', stacked=True, colormap='viridis')

# Set labels and title
plt.xlabel('Month')
plt.ylabel('Number of Crashes')
plt.title('Number of Crashes by Month and Year')

# Show the plot
plt.show()


import pandas as pd
from scipy.stats import chi2_contingency

# Assuming 'crash_filtered' is your DataFrame with relevant columns
contingency_table = pd.crosstab(index=crash_filtered['weather_condition'],
                                columns=[crash_filtered['lighting_condition'], crash_filtered['injuries']],
                                margins=True, margins_name='Total', rownames=['Weather'], colnames=['Lighting', 'Injuries'])

# Perform chi-square test for independence
chi2, p, _, _ = chi2_contingency(contingency_table)

# Output results
print(f"Chi-square value: {chi2}")
print(f"P-value: {p}")

# Interpret the results based on the p-value
if p < 0.05:
    print("There is a significant association between weather_condition, lighting_condition, and injuries.")
else:
    print("There is no significant association between weather_condition, lighting_condition, and injuries.")

Chi-square value: 548.9353777929671
P-value: 4.151392192467228e-80
There is a significant association between weather_condition, lighting_condition, and injuries.


##WHAT is the spatial distribution of different causes of accidnets?


import matplotlib.pyplot as plt
import pandas as pd

# Assuming 'latitude', 'longitude', 'injuries', and 'prim_contributory_cause' are columns in your DataFrame
latitudes = crash_filtered['latitude'].astype(float)
longitudes = crash_filtered['longitude'].astype(float)
injuries = crash_filtered['injuries']
prim_contributory_cause = crash_filtered['prim_contributory_cause']

# Convert injuries to numeric values (boolean to int)
injuries_numeric = injuries.astype(int)

# Define colors based on primary contributory cause
color_mapping = {
    'FAILING TO YIELD RIGHT-OF-WAY': 'red',
    'WEATHER': 'blue',
    'DRIVING SKILLS/KNOWLEDGE/EXPERIENCE': 'green',
    'FOLLOWING TOO CLOSELY': 'yellow',# Add more colors if needed
}

colors = prim_contributory_cause.map(color_mapping).fillna('gray')  # Use gray for unknown causes

# Create a scatter plot with colors based on primary contributory cause
plt.scatter(longitudes, latitudes, c=colors, marker='o', alpha=0.8)

# Set labels and title
plt.xlabel('Longitude')
plt.ylabel('Latitude')
plt.title('Primary Causes of Crashes')
#legend_labels = [plt.Line2D([0], [0], marker='o', color='w', markerfacecolor=color, markersize=10) for color in color_mapping.values()]
#plt.legend(legend_labels, color_mapping.keys(), title='Contributory Causes', loc='best')

# Show the plot
plt.show()


import plotly.express as px
import pandas as pd

# Assuming 'latitude', 'longitude', 'injuries', and 'prim_contributory_cause' are columns in your DataFrame
latitudes = crash_filtered['latitude'].astype(float)
longitudes = crash_filtered['longitude'].astype(float)
injuries = crash_filtered['injuries']
prim_contributory_cause = crash_filtered['prim_contributory_cause']

# Convert injuries to numeric values (boolean to int)
injuries_numeric = injuries.astype(int)

# Define colors based on primary contributory cause
color_mapping = {
    'FAILING TO YIELD RIGHT-OF-WAY': 'red',
    'WEATHER': 'blue',
    'DRIVING SKILLS/KNOWLEDGE/EXPERIENCE': 'green',
    'FOLLOWING TOO CLOSELY': 'yellow',  # Add more colors if needed
}

colors = prim_contributory_cause.map(color_mapping).fillna('gray')  # Use gray for unknown causes

# Create a DataFrame for Plotly
plotly_data = pd.DataFrame({'latitudes': latitudes, 'longitudes': longitudes, 'colors': colors})

# Create an interactive map plot with colors based on primary contributory cause
fig = px.scatter_mapbox(plotly_data,
                        lat='latitudes',
                        lon='longitudes',
                        color='colors',
                        color_discrete_map=color_mapping,
                        zoom=10)

# Set title
fig.update_layout(title='Primary Causes of Crashes')

# Show the interactive plot
fig.show()


pip install plotly

Collecting plotly
  Downloading plotly-5.18.0-py3-none-any.whl (15.6 MB)
     |████████████████████████████████| 15.6 MB 8.2 MB/s eta 0:00:01
Collecting tenacity>=6.2.0
  Downloading tenacity-8.2.3-py3-none-any.whl (24 kB)
Requirement already satisfied: packaging in /Users/aidan/opt/anaconda3/lib/python3.9/site-packages (from plotly) (21.0)
Requirement already satisfied: pyparsing>=2.0.2 in /Users/aidan/opt/anaconda3/lib/python3.9/site-packages (from packaging->plotly) (3.0.4)
Installing collected packages: tenacity, plotly
Successfully installed plotly-5.18.0 tenacity-8.2.3
Note: you may need to restart the kernel to use updated packages.

Exploratory Data Analysis¶

Exploratory Data Analysis¶

	longitude	latitude	injuries	lighting_condition	weather_condition	crash_month	prim_contributory_cause	sec_contributory_cause	crash_date
0	-87.775099001	41.909868519	False	DARKNESS, LIGHTED ROAD	CLEAR	2	FAILING TO REDUCE SPEED TO AVOID CRASH	UNABLE TO DETERMINE	2024-02-05 00:02:00
1	-87.631851672	41.911257045	False	DARKNESS, LIGHTED ROAD	CLEAR	2	DISREGARDING TRAFFIC SIGNALS	NOT APPLICABLE	2024-02-04 22:27:00
2	-87.633011933	41.912503239	False	DARKNESS, LIGHTED ROAD	CLEAR	2	UNABLE TO DETERMINE	UNABLE TO DETERMINE	2024-02-04 22:15:00
3	-87.675292438	42.002600373	False	DARKNESS, LIGHTED ROAD	CLEAR	2	UNDER THE INFLUENCE OF ALCOHOL/DRUGS (USE WHEN...	NOT APPLICABLE	2024-02-04 22:00:00
4	-87.753893377	41.925831886	False	DARKNESS, LIGHTED ROAD	CLEAR	2	UNABLE TO DETERMINE	UNABLE TO DETERMINE	2024-02-04 21:42:00
...	...	...	...	...	...	...	...	...	...
995	-87.624252186	41.743546758	False	DAYLIGHT	CLEAR	1	NOT APPLICABLE	NOT APPLICABLE	2024-01-31 16:12:00
996	-87.767138108	41.882099191	False	DAYLIGHT	CLEAR	1	OPERATING VEHICLE IN ERRATIC, RECKLESS, CARELE...	NOT APPLICABLE	2024-01-31 16:00:00
997	-87.687248767	41.917103631	False	DAYLIGHT	CLEAR	1	DRIVING SKILLS/KNOWLEDGE/EXPERIENCE	DRIVING SKILLS/KNOWLEDGE/EXPERIENCE	2024-01-31 15:54:00
998	-87.76844737	41.943227521	False	DAYLIGHT	CLEAR	1	FOLLOWING TOO CLOSELY	FOLLOWING TOO CLOSELY	2024-01-31 15:50:00
999	-87.651162183	41.869615798	False	DAYLIGHT	CLEAR	1	FAILING TO YIELD RIGHT-OF-WAY	NOT APPLICABLE	2024-01-31 15:49:00